Research map / Architectures and efficiency / RNNs and normalization
The streaming rollout of deep networks - towards fully model-parallel execution
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use streaming instead of sequential rollout | MNIST FF network · Noisy MNIST | classification accuracy | No clear effect |
| Use streaming instead of sequential rollout | MNIST S network · Noisy MNIST | early classification accuracy | Helped |
| Use streaming instead of sequential rollout | MNIST S network · Noisy MNIST | first response time: 1 update step earlier | Helped |
| Use streaming instead of sequential rollout | MNIST S network · Noisy MNIST | long-run classification accuracy | No clear effect |
| Use streaming instead of sequential rollout | MNIST S network · Noisy MNIST | input sampling frequency: F(R^{\text{str}}) = 1; F(R^{\text{seq}}) = 3 | Helped |
| Use streaming instead of sequential rollout | CIFAR10 DSR2 · Noisy CIFAR10 | early classification accuracy | Helped |
| Use streaming instead of sequential rollout | CIFAR10 DSR2 · Noisy CIFAR10 | first response time: $2$ update steps earlier | Helped |
| Increase network depth while using streaming rather than sequential rollout | CIFAR10 DSR0–DSR6 · Noisy CIFAR10 | early classification accuracy | Helped |
| Use streaming instead of sequential rollout | CIFAR10 DSR0–DSR6 · Noisy CIFAR10 | first response time | Helped |
| Use streaming instead of sequential rollout | GTSRB DSR4 without self-recurrence · GTSRB sequences | classification accuracy | Helped |
| Use streaming instead of sequential rollout | GTSRB DSR4 without self-recurrence · GTSRB sequences at greater object distances | final classification accuracy | Helped |
Closest papers by meaning
- Auto-reconfiguration for Latency Minimization in CPU-based DNN Serving (ICML 2025 · similarity 0.86)
- Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity (ICML 2025 · similarity 0.84)
- Deep Fusion: Efficient Network Training via Pre-trained Initializations (ICML 2024 · similarity 0.84)
- Don’t Think It Twice: Exploit Shift Invariance for Efficient Online Streaming Inference of CNNs (AAAI 2025 · similarity 0.84)
- Entropy-Gated Latent Recursion (NeurIPS 2026 · similarity 0.84)
- EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts (NeurIPS 2026 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.